Free EMR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to EMR and EHR for FREE!

This Futurist Says AI Will Never Replace Physicians

Posted on June 6, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

Most of us would agree that AI technology has amazing — almost frightening — potential to change the healthcare world. The thing is, no one is exactly sure what form those changes will take, and some fear that AI technologies will make their work obsolete. Doctors, in particular, worry that AI will undercut their decision-making process or even take their jobs.

Their fears are not entirely misplaced. Vendors in the healthcare AI world insist that their products are intended solely to support care, but of course, they need to say that. It’s not surprising that doctors fret as AI software starts to diagnose conditions, triage patients and perform radiology readings.

But according to medical futurist Bertalan Mesko, MD, Ph.D., physicians have nothing to worry about. “AI will transform the meaning of what it means to be a doctor; some tasks will disappear while others will be added to the work routine,” Mesko writes. “However, there will never be a situation where the embodiment of automation, either a robot or an algorithm, will take the place of a doctor.”

In the article, Mesko lists five reasons why he takes this position:

  1. Empathy is irreplaceable: “Even if the array of technologies will offer brilliant solutions, it would be difficult for them to mimic empathy,” he argues. “… We will need doctors holding our hands while telling us about life-changing diagnoses, their guide to therapy and their overall support.”
  2. Physicians think creatively: “Although data, measurements and quantitative analytics are a crucial part of a doctor’s work…setting up a diagnosis and treating a patient is not a linear process. It requires creativity and problem-solving skills that algorithms and robots will ever have,” he says.
  3. Digital technologies are just tools: “It’s only doctors together with their patients who can choose [treatments], and only physicians can evaluate whether the smart algorithm came up with potentially useful suggestions,” Mesko writes.
  4. AI can’t do everything: “There are responsibilities and duties which technologies cannot perform,” he argues. “… There will always be tasks where humans will be faster, more reliable — or cheaper than technology.”
  5. AI tech isn’t competing with humans: “Technology will help bring medical professionals towards a more efficient, less error-prone and more seamless healthcare,” he says. “… The physician will have more time for the patient, the doctor can enjoy his work in healthcare will move into an overall positive direction.”

I don’t have much to add to his analysis. I largely agree with what he has to say.

I do think he may be wrong about the world needing physicians to make all diagnoses – after all, a sophisticated AI tool could access millions of data points in making patient care recommendations. However, I don’t think the need for human contact will ever go away.

Patient Satisfaction Drops After Ambulatory EHR Is Rolled Out

Posted on June 4, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

In theory, EHR implementations are supposed to not only make providers’ jobs easier but ultimately, improve patient satisfaction too. The idea is that EHRs will eventually add something beneficial to physician routines and ultimately improving care processes. Of course, there’s a lot of question as to whether EHRs can now or will ever do so, but researchers continue to look at different use cases.

For example, new research published in JAMIA has concluded that while they weren’t too thrilled by the ambulatory EHR they were using, a group of OB/GYN practices showed some enthusiasm once the outpatient EHR was attached to the one collecting data on their related inpatient perinatal unit.

The purpose of the study was to look at how the installation of the ambulatory EHR within the OB/GYN practices and subsequent connection to an inpatient perinatal EHR affected providers’ attitudes toward sharing of clinical information. It also looked at the impact all of this had on patient satisfaction.

To conduct the study, researchers collected data on both provider and patient satisfaction. They assessed provider satisfaction by conducting four surveys staged across the phased implementation of the EHR. To measure patient satisfaction, meanwhile, they drew on data from Press Ganey surveys managed by the healthcare network using the usual process.

Their ultimate goal was to determine how provider and patient perceptions changed as the EHR system enabled greater information flow between the OB/GYN practices in the hospital.

What the study found was that the outpatient OB/GYN providers were less satisfied with how the EHR affected their work processes than other clinical and non-clinical staff. On the other hand, they grew more satisfied with their access to information once the inpatient perinatal triage unit offered useful functions. Specifically, they were happier with their access to information from the inpatient system once its capabilities included the ability to send automatic data flows from triage back to the OB/GYN offices.

On the other hand, overall patient reactions to the project appeared to be negative. Patient satisfaction fell after the installation of the ambulatory EHR, and researchers could find no evidence that patient satisfaction rebounded after the information sharing process began between inpatient and outpatient settings.

In summary, the study concluded, if providers are dissatisfied with their EHR system, and those difficulties undercut patient care, the process could negatively impact patient satisfaction. The authors recommended that healthcare organizations take extra care to maintain good communication with patients during this process.

Recording Doctor-Patient Visits Shows Great Potential

Posted on June 1, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

Doctors, do you know how you would feel if a patient recorded their visit with you? Would you choose to record them if you could? You may soon find out.

A new story appearing in STAT suggests that both patients and physicians are increasingly recording visits, with some doctors sharing the audio recording and encouraging patients to check it out at home.

The idea behind this practice is to help patients recall their physician’s instructions and adhere to treatment plans. According to one source, patients forget between 40% to 80% of physician instructions immediately after leaving the doctor’s office. Sharing such recordings could increase patient recall substantially.

What’s more, STAT notes, emerging AI technologies are pushing this trend further. Using speech recognition and machine learning tools, physicians can automatically transcribe recordings, then upload the transcription to their EMR.

Then, health IT professionals can analyze the texts using natural language processing to gain more knowledge about specific diseases. Such analytics are likely to be even more helpful than processes focused on physician notes, as voice recordings offer more nuance and context.

The growth of such recordings is being driven not only by patients and their doctors, but also by researchers interested in how to best leverage the content found in these recordings.

For example, a professor at Dartmouth is leading a project focused on creating an artificial intelligence-enabled system allowing for routine audio recording of conversations between doctors and patients. Paul Barr is a researcher and professor at the Dartmouth Institute for Health Policy and Clinical Practice.

The project, known as ORALS (Open Recording Automated Logging System), will develop and test an interoperable system to support routine recording of patient medical visits. The fundamental assumption behind this effort is that recording such content on smart phones is inappropriate, as if the patient loses their phone, their private healthcare information could be exposed.

To avoid this potential privacy breach, researchers are storing voice information on a secure central server allowing both patients and caregivers to control the information. The ORALS software offers both a recording and playback application designed for recording patient-physician visits.

Using the system, patients record visits on their phone, have them uploaded to a secure server and after that, have the recordings automatically removed from the phone. In addition, ORALS also offers a web application allowing patients to view, annotate and organize their recordings.

As I see it, this is a natural outgrowth of the trailblazing Open Notes project, which was perhaps the first organization encouraging doctors to share patient information. What makes this different is that we now have the technology to make better use of what we learn. I think this is exciting.

Nurse Satisfaction With EHRs Rises Dramatically, But Problems Remain

Posted on May 18, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

In the past, nurses despised EHRs as much as doctors did – perhaps even more. In fact, in mid-2014, 92% of nurses surveyed weren’t satisfied with the EHR they used, according to a study by Black Book Research. But things have changed a lot since then, Black Book says. The following data is focused largely on hospital-based nursing, but I think many of these data points are relevant to medical practices too.

Despite their previous antipathy to EHR’s, as of Q2 2018, 96% of nurses told Black Book that they wouldn’t want to go back to using paper records. That score is up 24% since 2016, the research firm reports.

Part of the reason the nurses are happier is that they feel they’re getting the technical support they need. Eighty-eight percent of responding nurses said that their IT departments and administrators were responding quickly when they asked for EHR changes, as compared with 30% in 2016.

On the other hand, the study also noted that when hospitals outsource the EHR helpdesk, nurses don’t always like the experience. Twenty-one percent said their experience with the EHR’s call center didn’t meet their expectations for communication skills and product knowledge. On the other hand, that’s a huge improvement from 88% in 2016.

Not only that, RNs are eager to improve their EHR skillsets. Most nurses are now glad that they are skilled at using at least one EHR, and 65% believe that persons who are skilled at working with multiple systems are seen as highly-desirable job candidates by health systems.

Providers’ choice of EHR can be an advantage for some in attracting top dressing talented. Apparently, RNs are beginning to choose job openings for the EHR product and vendor the provider uses as an indication of how the working environment may be than the provider itself. Eighty percent of job-seeking RNs reported that the reputation of the hospital’s EHR system is one of the top three considerations impacting where they choose to work.

That being said, there are still some IT issues that concern nurses. Eighty-two percent of nurses in inpatient facilities said they don’t have computers in each room or handheld/mobile devices they can use to access the EHR. That number is down from 93% in 2016, but still high.

These statistics should be of great interest to both hospitals and physicians. Obviously, hospitals have an institutional interest in knowing how nurses feel about their EHR platform and how they supported. Meanwhile, while most average size practices don’t address the same IT issues faced by hospitals, it benefits them to know what their nurses are looking for in a system. There’s much to think about here.

How Will CMS Handle Issues Surrounding MACRA Changes?

Posted on May 14, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

As most readers will know, when CMS released details on MIPS and the Alternative Payment Model incentives it embarked on a new direction for quality programs generally. As most readers will know, MIPS consolidated PQRS, the Physician Value-based Modifier and the Medicare EHR Incentive Program for EPs (Meaningful Use). But CMS is still updating the Medicaid incentive program.

If I were a physician, I’d be even more interested in the CMS initiative dubbed Promoting Interoperability. In some of the biggest news to come out of the agency in ages, CMS is restructuring the EHR Incentive Programs to become the Promoting Interoperability Programs. Promoting Interoperability replaces the Advancing Care Information category of MIPS.

Whoa. That would be a big enough deal on its own, but the issues the rule raises are an even bigger one.

CMS’s has been working towards this goal for a few years. Per HIMSS, here are some changes suggested in the proposed rule that might have the biggest impact on the health IT world:

  • The rule would cut down measures from 16 to six
  • It would use a new performance-based scoring methodology which would include measures of performance on e-prescribing, health information exchange, provider to patient exchange and public health and clinical data exchange
  • The agency will define and work to prevent “information blocking”

On a related note, CMS has posted a request for information asking for stakeholder feedback on program participation conditions. This is pretty unusual for the agency.

Like many CMS proposals, this one leaves some important questions open. (Apparently, CMS itself wonders how this thing will work, as the request for information suggests.)

For example, the new performance-based scoring method will award providers anywhere from 0 to 100 points. Measuring health IT performance is always a tricky thing to do, and there’s little doubt that if this becomes a final rule, both providers and CMS will have to go through some struggles before they perfect this approach. In the meantime, providers face some big challenges. How will they adapt to them? Its too soon to say.

Addressing so-called “information blocking” should be an even bigger challenge. Everyone from members of Congress to providers to vendors acts as though there’s one way to describe this practice, but there’s still a lot of wiggle room. Honestly, I’ll be amazed if CMS manages to pin it down the first time around.

Still, the time is more than overdue for CMS to take on interoperability directly. Without real data interoperability, many promising digital health schemes will collapse under their own weight. If CMS can figure out how to make it happen, it will be pretty neat.

Giving Patients Test Results: Is It A Good Idea?

Posted on May 2, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

These days, the conventional wisdom is that sharing health data with patients increases their engagement, which then improves their health.  And certainly, that may well be the case. I can tell you that when one of my doctors refused to share lab data until he reviewed it, I chewed his practice manager out. (Not very nice, I realized later.)

Still, I was intrigued by a story in the Washington Post challenging the idea that sharing test results is always a good idea. The story argues that in some cases, sharing data with patients lead to confusion and fear, largely because the patient usually gets no guidance on what the results mean. They may not be prepared to receive this information, and if they can’t reach their doctor, they might panic.

According to a source quoted in the Post, virtually no one knows what the actual benefits and risks are associated with releasing test results. “There is just not enough information about how it should be done right,” said Hardeep Singh, an associate professor at Baylor College of Medicine who studies patients’ experiences in receiving test results from portals. “There are unintended consequences for not thinking it through.”

Despite these concerns, some healthcare providers have decided to release most test results, gambling that this will pay off over the long-term. One such provider is Geisinger Health System. Geisinger releases test results twice a day, four hours after the data is published through a portal. ‘The majority [of patients] want early access to the results, and they don’t want to be impeded,” said Ben Hohmuth, Geisinger’s associate chief medical informatics officer at Geisinger.

Geisinger’s bet may help it avoid needless patient harm. According to a study appearing in JAMA, between 8% and 26% of abnormal test results – including potential malignancies – aren’t followed up on in a timely matter. Giving them this data allows them to react quickly to abnormal test results and advocate for themselves.

It also seems that the Washington Post didn’t take the time to get to know CT Lin, CMIO at University of Colorado Health. He’s done extensive research into providing electronic access to results and other health data. His results are clear and cover the idea that releasing some results is harmful. There are a few results that are good to keep until the provider has talked to the patient. However, he found across a wide range of examples that releasing the results doesn’t cause any of the damages that many imagine in their minds.

Maybe its time for providers to begin studying patient responses to test result access even more. We’re not talking rocket science here. You could start with an informal survey of patients visiting one of your primary care clinics, asking them whether they use your portal and which features they consider most valuable.

If patients don’t rate access to test results highly, it doesn’t mean that you shouldn’t bother making them available.  It could be that at the moment, your test results aren’t displayed in a useful manner, or that the patients you talk with dislike the portal overall. We can work to learn this as well rather than imagining some scenario that could go bad. That’s easy in healthcare.

Regardless, the evidence suggests that at least some patients benefit from having this data, especially the ability to ask good questions about their health status. For the time being, that’s probably a good enough reason to keep the data flowing.

AI Tool Helps Physician Group Manage Prescription Refills

Posted on April 25, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

Most of the time, when we hear about AI projects people are talking about massive efforts spanning millions of records and many thousands of patients. A recent blog item, however, suggests that AI can be used to improve comparatively modest problems faced by physician groups as well.

The case profiled in the blog involves Western Massachusetts-based Valley Medical Group, which is using machine learning to manage medication refills. The group, which includes 115 providers across four centers, implemented a product known as Charlie, a cloud-based tool made by Healthfinch 18 months ago. (I should note, at this point, that the blog maintained is by athenaHealth, which probably has a partnership with Healthfinch. Moving on…)

Charlie is a cloud-based tool which automates the process of prescription refills by integrating with EHRs. Charlie processes refill requests much like a physician or pharmacist would, but more quickly and probably more thoroughly as well.

According to the blog item, Charlie pulls in refill requests from the practice’s EHR then adds relevant patient data to the requests. After doing so, Charlie then runs the requests through an evidence-based rules engine to detect whether the request is in protocol or out of protocol. It also detects duplicates. errors and other problems. Charlie can also absorb specific protocols which let it know what to look for in each refill request it processes.

After 18 months, Valley’s refill process is far more efficient. Of the 10,000 refill requests that Valley gets every month, 60% are handled by a clerical person and don’t involve a clinician. In addition, clerical staff workloads have been cut in half, according to the practice’s manager of healthcare informatics.

Another benefit Valley saw from rolling out Charlie with that they found out which certain problems lay. For example, practice leaders found out that 20% of monthly refill requests were duplicate requests. Prior to implementing the new tool, practice staff spent a lot of time investigating the requests or worse, filling them by accident.

This type of technology will probably do a lot for medium-sized to larger practices, but smaller ones probably can’t afford to invest in this kind of technology. I have no idea what Healthfinch charges for Charlie, but I doubt it’s cheap, and I’m guessing its competitors are charging a bundle for this stuff as well. What’s more, as I saw at #HIMSS18, vendors are still struggling to define the right AI posture and product roadmap, so even if you have a lot of cash buying AI is still a somewhat risky play.

Still, if you’re part of a small practice that’s rethinking its IT strategy, it’s good to know that technologies like Charlie exist. I have little doubt that over time — perhaps fairly soon — vendors will begin offering AI tools that your practice can afford. In the meantime, it wouldn’t hurt to identify processes which seem to be wasting a lot of time or failing to get good results. That way, when an affordable tool comes along to help you’ll be ready to go.

Cloud-Based EHRs With Analytics Options Popular With Larger Physician Groups

Posted on April 20, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

Ever wonder what large medical practices want from the EHRs these days? According to one study, the answer is “cloud-based systems with all the bells and whistles.”

Black Book Research just completed a six-month client satisfaction poll questioning members of large practices about their EHR preferences. The survey collected data from roughly 19,000 EHR users.

According to the survey, 30% of practices with more than 11 clinicians expect to replace their current EHR by 2021, primarily because they want a more customizable system. It’s not clear whether they are sure yet which vendors offer the best customization options, though it’s likely we’ll hear more about this soon enough.

Among groups planning an EHR replacement, what appealed to them most (with 93% ranking it as their preferred option) was cloud-based mobile solutions offering an array of analytical options. They’re looking for on-demand data and actionable insights into financial performance, compliance tracking and tools to manage contractual quality goals. Other popular features included telehealth/virtual support (87%) and speech recognition solutions for hands-free data entry (82%).

Among those practices that weren’t prepared for an EHR replacement, it seems that some are waiting to see how internal changes within Practice Fusion and eClinicalWorks play out. That’s not surprising given that both vendors boasted an over 93% customer loyalty level for Q1 2018.

The picture for practices with less than six or fewer physicians is considerably different, which shouldn’t surprise anybody given their lack of capital and staff time.  In many cases, these smaller practices haven’t optimized the EHRs they have in place, with many failing to use secure messaging, decision support and electronic data sharing or leverage tools that increase patient engagement.

Large practices and smaller ones do have a few things in common. Ninety-three percent of all sized medical and surgical practices using an installed, functional EHR system are using three basic EHR tools either frequently or always, specifically data repositories, order entry and results review.

On the other hand, few small to midsize groups use advanced features such as electronic messaging, clinical decision support, data sharing, patient engagement tools or interoperability support. Again, this is a world apart from the higher-end IT options the larger practices crave.

For the time being, the smaller practices may be able to hold their own. That being said, other surveys by Black Book suggest that the less-digitalized practices won’t be able to stay that way for long, at least if they want to keep the practice thriving.

A related 2018 Black Book survey of healthcare consumers concluded that 91% of patients under 50 prefer to work with digitally-based practices, especially practices that offer conductivity with other providers and modern portals giving them easy access to the health data via both phones and other devices.

Pace of Technological Innovation

Posted on April 18, 2018 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

Sometimes you come across a chart that blows your mind and causes you to step back and reconsider your perspective. That’s what happened to me when I saw this chart shared by Sandeep Plum MD. The chart shows every major technological innovation in the last 150 years and how they have changed the way we work. More specifically, I think it shows how technology has improved the output we’re able to create.

This chart is pretty astonishing to consider. I’d like to dig into the data some more, but no doubt the concept of technology allowing us to produce more is something we’ve all experienced. The amount of leisure time we have compared to farmers even 150 years ago is astonishing to consider.

The problem in healthcare is that many people will wonder why healthcare hasn’t seen the same increase in output. The reality is that we have seen an improvement. The challenge in healthcare is the care we provide has become much more complex and the regulations around that care have become more complex as well. So, the increased output doesn’t feel the same because of these added complexities.

When thinking about healthcare complexity I always like to think about the country doctor back in the day that had the famous black bag and would visit you in your home. What diagnostic tools did he have? Not very much. What treatment options were available to him? Not very many (and a lot of them were very questionable). Compare that to today’s healthcare which has extremely sophisticated diagnostic tools and treatment options. Much of our increased output goes into navigating these tools and options.

The same is true for the increased regulation and reimbursement requirements. How did the country doc handle documentation and reimbursement? He might have written a few notes on a sheet of paper. Underscore the might. The country doc didn’t have to worry about insurance requirements, prior authorizations, CPT codes, or other complexities that make medical billing so time-consuming. He just asked the patient if they could pay. Sometimes that meant he was taking a pig home with him as payment, but he didn’t have to worry about insurance claims denials or sending out patient bills.

This is why I think so many doctors are frustrated by technology. The technology has improved their output, but in many ways that improved output has just been pushed to satisfy bureaucratic requirements as opposed to improving care and making the doctor more efficient.

The good news is that the pace of technological change will continue. It’s not too hard to see the day when a doctor goes into an exam room and the documentation that’s required for reimbursement and continuity of care just happens automatically. We’re not there yet, but the technology to make that a reality is. The only question is whether we can stem the increase in regulations that are eating away all that increased output that technology provides.

Almost 20 Percent of CDS Alert Dismissals May Be Inappropriate

Posted on April 13, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

The number of alerts generated by clinical decision support systems can be overwhelming for clinicians. It’s little wonder that the Joint Commission has long identified alert fatigue as a critical safety issue for providers, particularly given how many turn out to be unimportant or even irrelevant.

Unfortunately, however, there’s a flipside to this issue. Sometimes, CDS alerts can actually prevent care problems, clearly suggesting that clinicians shouldn’t dismiss them out of hand either. In fact, recently-published research found that at least in an ICU setting, overriding alerts might be associated with patient harm.

The study, which appeared in BMJ Quality & Safety, focused on the nature and impact of medication-related CDS overrides in the ICU. To conduct the analysis, the authors gathered data on adults admitted to any of six ICUs between July 2016 and April 2017.

The research team looked at a total of 2,448 overridden alerts from 712 unique patient encounters. The studies looked at patients with provider-overridden CDS alerts for dose, drug allergies, drug-drug interaction, geriatric and renal alerts. They also looked at how frequently patients suffered adverse drug events following alert overrides and the risk of adverse drug events given the appropriateness of the overrides.

A team of two independent reviewers concluded that while 81.6% of the overrides were appropriate, the roughly 19% remaining were inappropriate.

Researchers found that inappropriate overrides were associated with a greater risk of adverse drug events. In addition, they concluded that they could find more potential and definite adverse drug events following inappropriate overrides than appropriate overrides. They also found that inappropriate overrides were associated with an increased risk of adverse drug events.

Overall, inappropriate overrides were six times as likely to be associated with potential and definite adverse drug events.  That’s too big a correlation to ignore.

One thing the study doesn’t comment on is how the alerts were presented. Given that they may have been presented through multiple interfaces, the question arises of how big a difference those interfaces make in how clinicians respond to alerts. It could be that these interfaces have more impact than the clinical content of the alerts.

Bottom line, this problem may very well fall under the larger umbrella of usability problems. Just one more reason why the industry needs to keep a laser focus on improving usability in HIT across the board.